RFQ through negotiation, inside the guardrails you set.
Describe the need in a short brief and the Sourcing Agent drafts the RFQ, suggests suppliers by category, collects bids, scores them on weighted criteria, and runs up to three negotiation rounds per supplier before recommending an award with savings vs budget.
How it works
The same pipeline you see in the live module, step by step.
- 1
Parse the brief
Extract quantity, category, delivery window, and unit from plain language and estimate budget from catalog or historical pricing.
- 2
Publish the RFQ
Set evaluation criteria with weights that sum to 100%, invite qualified suppliers, and exclude blocked vendors.
- 3
Collect and score bids
Normalize cost, lead time, warranty, payment terms, and supplier risk into a weighted matrix and rank respondents.
- 4
Negotiate in rounds
Run guardrailed rounds — target price, walk-away, must-have warranty — with deterministic concession logic; Stellitron Intelligence phrases the messages.
- 5
Recommend award
Present the winning supplier, unit economics, and savings vs budget; award updates the event and logs impact.
Checks and rules
Deterministic logic runs on every action; optional AI enriches text when configured.
- Weighted criteria re-normalized to 100%
- Blocked suppliers excluded from invite list
- Total cost, lead time, warranty, Net terms, and risk in score
- Negotiation floor per supplier tier and spend leverage
- Must-have warranty and walk-away price enforced
- Award logged with budget vs awarded total
What you get
Artifacts land in the shared procurement record and activity log.
- Structured RFQ with criteria sliders
- Bid table with round history
- Evaluation matrix and ranked totals
- Negotiation transcript with offer chips
- Award recommendation with rationale bullets
Where teams use Sourcing Agent
Questions
Does it need my ERP?
The live demo runs on a shared procurement record (requests, POs, receipts, invoices, contracts, and spend). In production you connect your ERP or AP system via API or scheduled file exchange so matching uses your real PO and goods-receipt data. Until then, every rule runs the same way on the demo dataset.
Does it depend on an AI model to work?
No. Every decision runs through Stellitron's deterministic rules first: tolerance math, playbook comparisons, weighted bid scoring and classification maps, so results are repeatable and auditable. Stellitron Intelligence adds document reading, drafting and plain-language explanations on top, and the agents keep working if it is unavailable.
Who approves?
Agents recommend and trace; people approve. Intake routes to managers, category owners, Finance, and the CPO by amount and category. Invoices on exception stay on hold until AP approves, requests a credit note, or rejects a duplicate. Contracts, sourcing awards, and supplier blocks follow your owners in the app — the agent surfaces the evidence, not the signature.
Are supplier responses real?
In the demo, bids and concessions are simulated deterministically from catalog price, lead time, and supplier profile so runs are reproducible. Production connects to your supplier portal or email intake.
Who awards the contract?
A procurement owner clicks Award after reviewing the recommendation. The agent does not sign contracts; it documents why one bid leads on weighted criteria.